Next Article in Journal
Kawasaki Disease with Hepatobiliary Manifestations
Next Article in Special Issue
Hospitalization Duration for Acute Myocardial Infarction: A Temporal Analysis of 18-Year United States Data
Previous Article in Journal
Intestinal Mucosa-Associated Lymphoid Tissue Lymphoma Transforming into Diffuse Large B-Cell Lymphoma in a Young Adult Patient with Neurofibromatosis Type 1: A Case Report
Previous Article in Special Issue
Exploring the Potential Use of Wearable Devices as a Prognostic Tool among Patients in Hospice Care
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Medicina
Volume 58
Issue 12
10.3390/medicina58121831
medicina-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles thumb_up
...
Endorse textsms
...
Comment
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Clinical Phenotypes of Dual Kidney Transplant Recipients in the United States as Identified through Machine Learning Consensus Clustering

by
Supawit Tangpanithandee
1,2,
Charat Thongprayoon
1,
Caroline C. Jadlowiec
3,
Shennen A. Mao
4,
Michael A. Mao
5,
Pradeep Vaitla
6,
Napat Leeaphorn
5,
Wisit Kaewput
7,
Pattharawin Pattharanitima
8,
Pajaree Krisanapan
1,8,
Pitchaphon Nissaisorakarn
9,
Matthew Cooper
10 and
Wisit Cheungpasitporn
1,*
1
Division of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USA
2
Chakri Naruebodindra Medical Institute, Faculty of Medicine Ramathibodi Hospital, Mahidol University, Samut Prakan 10540, Thailand
3
Division of Transplant Surgery, Mayo Clinic, Phoenix, AZ 85054, USA
4
Division of Transplant Surgery, Mayo Clinic, Jacksonville, FL 32224, USA
5
Division of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Jacksonville, FL 32224, USA
6
Division of Nephrology, University of Mississippi Medical Center, Jackson, MS 39216, USA
7
Department of Military and Community Medicine, Phramongkutklao College of Medicine, Bangkok 10400, Thailand
8
Division of Nephrology, Department of Internal Medicine, Thammasat University, Bangkok 12120, Thailand
9
Department of Medicine, Division of Nephrology, Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USA
10
Medstar Georgetown Transplant Institute, Georgetown University School of Medicine, Washington, DC 21042, USA
*
Author to whom correspondence should be addressed.
Medicina 2022, 58(12), 1831; https://doi.org/10.3390/medicina58121831
Submission received: 24 October 2022 / Revised: 3 December 2022 / Accepted: 9 December 2022 / Published: 12 December 2022
(This article belongs to the Special Issue Clinical Studies, Big Data, and Artificial Intelligence in Medicine)
Browse Figures
Review Reports Versions Notes

Abstract

:
Background and Objectives: Our study aimed to cluster dual kidney transplant recipients using an unsupervised machine learning approach to characterize donors and recipients better and to compare the survival outcomes across these various clusters. Materials and Methods: We performed consensus cluster analysis based on recipient-, donor-, and transplant-related characteristics in 2821 dual kidney transplant recipients from 2010 to 2019 in the OPTN/UNOS database. We determined the important characteristics of each assigned cluster and compared the post-transplant outcomes between clusters. Results: Two clinically distinct clusters were identified by consensus cluster analysis. Cluster 1 patients was characterized by younger patients (mean recipient age 49 ± 13 years) who received dual kidney transplant from pediatric (mean donor age 3 ± 8 years) non-expanded criteria deceased donor (100% non-ECD). In contrast, Cluster 2 patients were characterized by older patients (mean recipient age 63 ± 9 years) who received dual kidney transplant from adult (mean donor age 59 ± 11 years) donor with high kidney donor profile index (KDPI) score (59% had KDPI ≥ 85). Cluster 1 had higher patient survival (98.0% vs. 94.6% at 1 year, and 92.1% vs. 76.3% at 5 years), and lower acute rejection (4.2% vs. 6.1% within 1 year), when compared to cluster 2. Death-censored graft survival was comparable between two groups (93.5% vs. 94.9% at 1 year, and 89.2% vs. 84.8% at 5 years). Conclusions: In summary, DKT in the United States remains uncommon. Two clusters, based on specific recipient and donor characteristics, were identified through an unsupervised machine learning approach. Despite varying differences in donor and recipient age between the two clusters, death-censored graft survival was excellent and comparable. Broader utilization of DKT from high KDPI kidneys and pediatric en bloc kidneys should be encouraged to better address the ongoing organ shortage.

1. Introduction

Kidney transplantation is widely acknowledged as the most effective modality of renal replacement therapy for patients with end-stage kidney disease (ESKD). It not only increases expected patient survival as compared to chronic dialysis but also improves the quality of life [1,2,3]. However, there is a large gap between the number of patients receiving a transplant and the number of people waiting due to a limited number of donor organs [4,5]. Moreover, after the Organ Procurement and Transplantation Network (OPTN) introduced the kidney donor profile index (KDPI) as a new national deceased donor kidney allocation policy in 2013 [6], the kidney discard rate in the US greatly rose from 10% in 1998 to 21% in 2020 [7]. As a result, there have been ongoing efforts by the transplant community to increase the size of the deceased donor pool by using more kidneys from expanded criteria (ECD) and high KDPI donors, donation after cardiocirculatory death donors, as well as standard criteria donors with prolonged warm or cold ischemic times (CIT), acute kidney injury donors, and donors at the extremes of age [7]. Application of DKT of these discard at-risk groups has been another proposed strategy to further maximized transplant opportunities.
DKT is a strategy used in kidney transplantation to augment nephron mass in higher-risk transplant kidneys [8,9]. DKT is most often performed when donors are very young or very old and dual utilization allows compensation for healthy but limited renal mass or baseline chronic changes [10,11]. To date, reported graft survival outcomes in adult DKT compared to ECD single kidney transplantation (SKT) remain limited although several studies have been suggestive of outcomes with DKT [11,12,13,14,15,16,17,18,19,20,21,22]. Similarly, there continues to be heterogeneity for small pediatric donors with a dual versus single consideration recommended for those donors weighting >15 kg [11,23]. Although numerous studies have focused on defining optimal allocation criteria for pediatric and adult DKT, a machine learning technique has yet to be applied [12,17,18,19,20,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40].
Machine learning is a subfield of artificial intelligence that has been applied to assist clinicians in making better clinical decisions in various areas of the medical field [41,42,43]. Generally, machine learning provides three types of algorithms: supervised, unsupervised, and reinforcement learning [41,42,43]. By identifying certain similarities and differences in various input variables, a computer system can complete a task without explicit programming. This is known as unsupervised machine learning [41,42,43,44]. As a result, grouping data into clinically relevant clusters can aid clinicians [42,43,45,46,47]. In this study, an unsupervised machine learning clustering approach was used to identify distinct clusters of DKT recipients and their clinical outcomes using the OPTN/UNOS database from 2010 through 2019.

2. Materials and Methods

2.1. Data Source and Study Population

We screened renal transplant patients the OPTN/UNOS database (2010 to 2019) to identify adult DKT patients in the United States. We excluded patients who received simultaneous kidney transplants with other organs. The study was approved by the Ethics Board of the Mayo Clinic (IRB ID: 21-007698).

2.2. Data Collection

We abstracted the comprehensive list of recipient-, donor-, and transplant-related characteristics, as shown in Table 1, to include in cluster analysis. KDPI was calculated based on donor age, height, weight, race, history of hypertension, diabetes mellitus, hepatitis C, cause of death, serum creatinine, and donor after cardiac death criteria. KDPI score ranges from 0–100% with higher score indicating lower quality donor kidneys. All variables had missing data of <5%, and multivariable imputation by chained equation (MICE) method was subsequently utilized [48].

2.3. Clustering Analysis

ML was utilized via an unsupervised consensus clustering analysis to categorize clinical phenotypes of DKT recipients [44]. To prevent producing an excessive number of clusters, we applied a subsampling parameter of 80% with 100 iterations and a number of potential clusters (k) ranging from 2 to 10. The optimal number of clusters was established by appraising the consensus matrix (CM) heat map, cumulative distribution function (CDF), and cluster-consensus plots with the within-cluster consensus scores. The average consensus value for all pairings of individual belonging to the same cluster was determined as the within-cluster consensus score, which ranged from 0 to 1 [49]. A closer value to 1 suggests more cluster stability. The full description of the consensus cluster algorithms utilized in this study are provided in Supplementary Materials.

2.4. Outcomes

Post-transplant outcomes included (1) patient death, and (2) 1- and 5-year death-censored allograft loss, and (3) acute allograft rejection within 1 year post-transplant. Patients were censored for death at the last follow-up date reported to the OPTN/UNOS database, thus death-censored graft failure was defined as the need for dialysis or kidney retransplantation.

2.5. Statistical Analysis

After we categorized adult DKT patients by the consensus clustering algorithm, the characteristics and outcomes among the assigned clusters were compared. The difference in clinical characteristics was tested by utilizing Student’s t-test for continuous data and Chi-squared test for categorical data. The key characteristics of clusters were identified by applying the standardized mean difference between each cluster and the overall cohort with the pre-specified cut-off of >0.3. We demonstrated the risk of death-censored graft failure and patient death after kidney retransplant using Kaplan–Meier plot. We calculated the hazard ratio (HR) for death-censored graft loss, and mortality using Cox proportional hazard analysis. Because the date of rejection was not reported in the OPTN/UNOS database, we calculated the odds ratio (OR) for 1-year rejection using logistic regression analysis. We did not adjust the association of the assigned clusters with post-transplant outcomes for clinical characteristics because clinically distinct clusters were purposefully generated from the consensus clustering approach. R, version 4.0.3 (RStudio, Inc., Boston, MA, USA; http://www.rstudio.com/, accessed on 21 July 2021); ConsensusClusterPlus package (version 1.46.0) and the MICE command in R were used for consensus clustering analysis and for multivariable imputation by chained equation, respectively [48].

3. Results

From 2010 to 2019, there were total 158,367 kidney transplant recipients in the U.S. Of these, 2821 (1.8%) underwent DKT. Consensus clustering analysis was applied into these 2821 DKT recipients. The CDF plot demonstrated the consensus distributions for each cluster (Figure 1A). The delta area plot revealed the relative change in the area under the CDF curve (Figure 1B). The greatest changes in the area were identified between k = 2 and k = 4, after which point the relative rise in area decreased substantially. As shown in the CM heatmap (Figure 1C and Supplementary Figures S1–S9), the ML algorithm identified cluster 2 with distinct borders, demonstrating high cluster stability across repeated iterations. The mean cluster consensus score was highest in two clusters (Figure 2). Thus, consensus clustering analysis identified two clinically distinct clusters of DKT recipients.

3.1. Characteristics of Each DKT Cluster

There were 1875 (66%) patients in Cluster 1, and 946 (34%) patients in Cluster 2. Table 1 and Figure 3 demonstrated characteristics of DKT patients according to the assigned clusters. Cluster 1 patients was characterized by younger patients (mean recipient age 49 ± 13 years) who received DKT from pediatric (mean donor age 3 ± 8 years) non-expanded criteria deceased donor (100% non-ECD). In contrast, Cluster 2 patients was characterized by older patients (mean recipient age 63 ± 9 years) who received DKT from adult (mean donor age 59 ± 11 years) donor with a high KDPI score (59% had KDPI ≥ 85). In total, 70% and 30% of transplanted kidneys were from ECD and non-ECD deceased donor, respectively.

3.2. Post-Transplant Outcomes of Each DKT Clusters

Table 2 shows post-transplant outcomes according to the assigned clusters. Cluster 1 patients had higher patient survival (98.0% vs. 94.6% at 1 year, and 92.1% vs. 76.3% at 5 years) compared to cluster 2 patients (Figure 4A), and it was consistent across subgroup analysis (Table 3). Cluster 1 and cluster 2 had comparable death-censored graft survival (93.5% vs. 94.9% at 1 year, and 89.2% vs. 84.8% at 5 years) (Figure 4B). However, Cluster 2 might be associated with higher risk of death-censored graft failure in male kidney transplant recipients or donors (Table 3). Cluster 1 had less acute rejection (4.2% vs. 6.1% within 1 year) compared to cluster 2 patients.

4. Discussion

DKT, the transplantation of two kidneys from the same donor into a single recipient, has been utilized as an alternative approach to expand the available donor pool [7,11]. Many reports show that the graft survival rate was higher in the DKT recipients than in those single kidney transplant (SKT) with ECD or high KDPI kidney [11,12,15,19]. According to our study, DKT remains uncommon in the United States, accounting for only 1.8% of the overall kidney transplants. Recent OPTN allocation changes took effect in 2019 and were further affected by implementation of the 250 nautical mile fixed circle allocation [50]. Despite policy intent, there was a decrease in the number of dual kidney transplants performed albeit initial monitoring occurred during the COVID pandemic.
In this study, we use an unsupervised machine learning consensus clustering approach to categorize DKT into two different clusters based on recipient and donor characteristics in the OPTN/UNOS database. Cluster 1 patients, which accounted for nearly 70% of all DKT, were younger patients who received DKT from pediatric non-ECD donors. In contrast, cluster 2 patients were characterized by older patients who received DKT from adult donors with higher KDPI scores.
Cluster 2 patients received higher KDPI kidneys and had higher incidence of delayed graft function, and thus higher acute rejection was observed in cluster 2 recipients when compared to cluster 1 patients. While it is perhaps not unexpected that patient survival was better in cluster 1 given that patients in cluster 1 were significantly younger and less likely to be diabetic as compared to those in cluster 2, death-censored graft survival was; however, comparable between the two clusters. Early graft losses due to technical complications likely account for decreased graft survival in pediatric DKT recipients along with increased probability of seeing recurrent primary disease within the allograft [51]. By comparison, recipient characteristics in combination with lower expected longevity in higher KDPI kidneys likely accounts for similarities in patient survival and death-censored graft loss for cluster 2. The findings of this study illustrate excellent death-censored graft survival in both clusters. This reflects appropriate donor-recipient pairing and kidney utilization in the transplant community. These data align with what has been observed within the OPTN post-policy implementation where a higher proportion of dual kidney recipients were aged 65+ year whereas the proportion of pediatric en bloc kidney transplants for recipients aged 18–34 and 35–49 years notably increased [50].
There are some limitations in this study. Due to the registry nature of this cohort, there is lack of detail specific to exact causes for graft loss and death as well as specific detail related to donor-recipient pairing and center-specific criteria for DKT utilization. Additionally, lack of difference in death-censored graft loss between the 2 clusters can be explained by differences in recipient and donor characteristics, which are not necessarily novel. Although these clusters clinically different, and the application of machine learning is novel, there are limitations in how these data will enhance current clinical decision-making. Future studies applying supervised machine learning with prediction models based upon this initial data will be of greater utility in assessing predictors of survival for DKT.
To the best of our knowledge, this is the first machine learning approach specifically targeted at DKT. Two DKT clusters were identified using machine learning clustering methods without human intervention. The outcomes of our clustering approach, based on machine learning, support existing studies demonstrating the importance of donor-recipient pairing in DKT outcomes which also highlights opportunities to improve the kidney allocation system in the United States. There are likely existing opportunities to further expand DKT utilization within the transplant community, particularly for high KDPI kidneys. The application of ML consensus clustering approach in this study provides a novel understanding of unique phenotypes of DKT recipients in order to advance allocation systems to expand the donor pool. Given excellent outcomes among both clusters, DKT from high KDPI kidneys and pediatric en bloc kidneys should be encouraged to better address the ongoing organ shortage.

5. Conclusions

In summary, DKT in the United States remains uncommon. Two clusters, based on specific recipient and donor characteristics, were identified through an unsupervised machine learning approach. Despite varying differences in donor and recipient age between the two clusters, death-censored graft survival was excellent and comparable. Broader utilization of DKT from high KDPI kidneys and pediatric en bloc kidneys should be encouraged to better address the ongoing organ shortage.

Supplementary Materials

The following are available online at https://0-www-mdpi-com.brum.beds.ac.uk/article/10.3390/medicina58121831/s1. Figure S1. Consensus matrix heat map (k = 2) depicting consensus values on a white to blue color scale of each cluster; Figure S2. Consensus matrix heat map (k = 3) depicting consensus values on a white to blue color scale of each cluster; Figure S3. Consensus matrix heat map (k = 4) depicting consensus values on a white to blue color scale of each cluster; Figure S4. Consensus matrix heat map (k = 5) depicting con-sensus values on a white to blue color scale of each cluster; Figure S5. Consensus matrix heat map (k = 6) depicting consensus values on a white to blue color scale of each cluster; Figure S6. Consensus matrix heat map (k = 7) depicting consensus values on a white to blue color scale of each cluster; Figure S7. Consensus matrix heat map (k = 8) depicting consensus values on a white to blue color scale of each cluster; Figure S8. Consensus matrix heat map (k = 9) depicting con-sensus values on a white to blue color scale of each cluster; Figure S9. Consensus matrix heat map (k = 10) depicting consensus values on a white to blue color scale of each cluster. References [52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67] are cited in the supplementary materials.

Author Contributions

Conceptualization, S.T., C.T., C.C.J., S.A.M., M.A.M., P.V., N.L., W.K., P.P., P.K., P.N., M.C. and W.C.; Data curation, S.T., C.T., N.L. and W.C.; Formal analysis, S.T., C.T. and W.C.; Funding acquisition, W.C.; Investigation, S.T., C.T., C.C.J., W.K., P.K. and W.C.; Methodology, S.T., C.T., C.C.J., S.A.M., M.A.M., W.K., P.N. and W.C.; Project administration, W.C.; Resources, S.T., N.L. and W.C.; Software, S.T. and W.C.; Supervision, C.T., C.C.J., S.A.M., M.A.M., P.V., N.L., W.K., P.P., P.K., P.N., M.C. and W.C.; Validation, S.T., C.T., C.C.J., P.P. and W.C.; Visualization, S.T., C.T. and W.C.; Writing—original draft, S.T. and W.C.; Writing—review and editing, S.T., C.T., C.C.J., S.A.M., M.A.M., P.V., N.L., W.K., P.P., P.K., P.N., M.C. and W.C. All authors have read and agreed to the published version of the manuscript.

Funding

This research received no external funding.

Institutional Review Board Statement

The study was conducted in accordance with the Declaration of Helsinki and approved by the Ethics Board of the Mayo Clinic (IRB ID: 21-007698).

Informed Consent Statement

Patient consent was waived due to the minimal risk nature of observational chart review study.

Data Availability Statement

Data will be made available by the authors upon reasonable request.

Acknowledgments

Data sets were derived from OPTN/UNOS database. However, the authors are responsible for the interpretation and reporting of these data, which should in no way be considered as an official policy or interpretation by the OPTN or the United States government.

Conflicts of Interest

The authors declare no conflict of interest.

References

  1. Garcia, G.G.; Harden, P.; Chapman, J. The global role of kidney transplantation. Indian J. Nephrol. 2012, 22, 77–82. [Google Scholar] [CrossRef] [PubMed]
  2. Tonelli, M.; Wiebe, N.; Knoll, G.; Bello, A.; Browne, S.; Jadhav, D.; Klarenbach, S.; Gill, J. Systematic Review: Kidney Transplantation Compared with Dialysis in Clinically Relevant Outcomes. Am. J. Transplant. 2011, 11, 2093–2109. [Google Scholar] [CrossRef] [PubMed]
  3. Yang, F.; Liao, M.; Wang, P.; Yang, Z.; Liu, Y. The Cost-Effectiveness of Kidney Replacement Therapy Modalities: A Systematic Review of Full Economic Evaluations. Appl. Health Econ. Health Policy 2020, 19, 163–180. [Google Scholar] [CrossRef] [PubMed]
  4. Klein, A.S.; Messersmith, E.E.; Ratner, L.E.; Kochik, R.; Baliga, P.K.; Ojo, A.O. Organ Donation and Utilization in the United States, 1999–2008. Am. J. Transplant. 2010, 10, 973–986. [Google Scholar] [CrossRef] [PubMed]
  5. Wolfe, R.A.; Roys, E.C.; Merion, R.M. Trends in Organ Donation and Transplantation in the United States, 1999-2008. Am. J. Transplant. 2010, 10, 961–972. [Google Scholar] [CrossRef] [Green Version]
  6. Israni, A.K.; Salkowski, N.; Gustafson, S.; Snyder, J.J.; Friedewald, J.J.; Formica, R.N.; Wang, X.; Shteyn, E.; Cherikh, W.; Stewart, D.; et al. New National Allocation Policy for Deceased Donor Kidneys in the United States and Possible Effect on Patient Outcomes. J. Am. Soc. Nephrol. 2014, 25, 1842–1848. [Google Scholar] [CrossRef] [Green Version]
  7. Stratta, R.J.; Harriman, D.; Gurram, V.; Gurung, K.; Sharda, B. Dual kidney transplants from adult marginal donors: Review and perspective. Clin. Transplant. 2021, 36, e14566. [Google Scholar] [CrossRef]
  8. Johnson, L.B.; Kuo, P.C.; Dafoe, D.C.; Schweitzer, E.J.; Alfrey, E.J.; Klassen, D.K.; Hoehn-Sarie, E.W.; Weir, M.R.; Bartlett, S.T. Double adult renal allografts: A technique for expansion of the cadaveric kidney donor pool. Surgery 1996, 120, 580–584. [Google Scholar] [CrossRef]
  9. Johnson, L.B.; Kuo, P.C.; Dafoe, D.C.; Drachenberg, C.B.; Schweitzer, E.J.; Alfrey, E.J.; Ridge, L.A.; Salvatierra, P.; Papadimitriou, J.C.; Mergner, W.J.; et al. The Use of Bilateral Adult Renal Allografts-A Method to Optimize Function from Donor Kidneys with Suboptimal Neph-ron Mass. Transplantation 1996, 61, 1261–1263. [Google Scholar] [CrossRef]
  10. Das, D.M.; Heilman, R.L.; Khamash, H.A.; Mathur, A.K.; Singer, A.L.; Reddy, K.S.; Jadlowiec, C.C. Overcoming Mismatch Concerns for Adult Recipients of Small Pediatric Deceased Donor Kidneys. Transplant. Proc. 2021, 53, 1509–1513. [Google Scholar] [CrossRef]
  11. Das, D.; Wagler, J.; Ohara, S.; Nguyen, M.; Frasco, P.E.; Smith, M.; Khamash, H.; Mathur, A.K.; Budhiraja, P.; Reddy, K.; et al. Outcomes of dual kidney transplants from high KDPI kidneys are superior compared to single kidney high KDPI transplants at 1 year. Clin. Transplant. 2022, 36, e14737. [Google Scholar] [CrossRef]
  12. Andrés, A.; Morales, J.M.; Herrero, J.C.; Praga, M.; Morales, E.; Hernández, E.; Ortuño, T.; Rodício, J.L.; A Martínez, M.; Usera, G.; et al. Double Versus Single Renal Allografts from Aged Donors. Transplantation 2000, 69, 2060–2066. [Google Scholar] [CrossRef]
  13. Bunnapradist, S.; Gritsch, H.A.; Peng, A.; Jordan, S.C.; Cho, Y.W. Dual Kidneys from Marginal Adult Donors as a Source for Cadaveric Renal Transplantation in the United States. J. Am. Soc. Nephrol. 2003, 14, 1031–1036. [Google Scholar] [CrossRef] [Green Version]
  14. De Serres, S.A.; Caumartin, Y.; Noël, R.; Lachance, J.-G.; Côté, I.; Naud, A.; Fradet, Y.; Mfarrej, B.G.; Agharazii, M.; Houde, I. Dual-Kidney Transplants as an Alternative for Very Marginal Donors: Long-Term Follow-Up in 63 Patients. Transplantation 2010, 90, 1125–1130. [Google Scholar] [CrossRef]
  15. Fernández-Lorente, L.; Riera, L.; Bestard, O.; Carrera, M.; Gomà, M.; Porta, N.; Torras, J.; Melilli, E.; Gil-Vernet, S.; Grinyó, J.M.; et al. Long-Term Results of Biopsy-Guided Selection and Allocation of Kidneys from Older Donors in Older Recipients. Am. J. Transplant. 2012, 12, 2781–2788. [Google Scholar] [CrossRef]
  16. Gill, J.; Cho, Y.W.; Danovitch, G.M.; Wilkinson, A.; Lipshutz, G.; Pham, P.-T.; Gill, J.S.; Shah, T.; Bunnapradist, S. Outcomes of Dual Adult Kidney Transplants in the United States: An Analysis of the OPTN/UNOS Database. Transplantation 2008, 85, 62–68. [Google Scholar] [CrossRef] [Green Version]
  17. Impedovo, S.; de Lorenzis, E.; Volpe, A.; Gesualdo, L.; Grandaliano, G.; Palazzo, S.; Lucarelli, G.; Bettocchi, C.; Terrone, C.; Stratta, P.; et al. Middle and Long-term Outcomes of Dual Kidney Transplant: A Multicenter Experience. Transplant. Proc. 2013, 45, 1237–1241. [Google Scholar] [CrossRef]
  18. Sefora, P.E.; Silvio, S.; Nicola, D.F.; Giuseppe, R.; Iris, F.; Luigino, B.; Maria, G.; Eliana, G.; Donato, D.; Enrico, M.; et al. Optimizing utilization of kidneys from deceased donors over 60 years: Five-year outcomes after implementation of a combined clinical and histological allocation algorithm. Transpl. Int. 2013, 26, 833–841. [Google Scholar] [CrossRef]
  19. Remuzzi, G.; Cravedi, P.; Perna, A.; Dimitrov, B.D.; Turturro, M.; Locatelli, G.; Rigotti, P.; Baldan, N.; Beatini, M.; Valente, U.; et al. Long-Term Outcome of Renal Transplantation from Older Donors. N. Engl. J. Med. 2006, 354, 343–352. [Google Scholar] [CrossRef] [Green Version]
  20. Rigotti, P.; Capovilla, G.; Di Bella, C.; Silvestre, C.; Donato, P.; Baldan, N.; Furian, L. A single-center experience with 200 dual kidney transplantations. Clin. Transplant. 2014, 28, 1433–1440. [Google Scholar] [CrossRef]
  21. Snanoudj, R.; Timsit, M.-O.; Rabant, M.; Tinel, C.; Lazareth, H.; Lamhaut, L.; Martinez, F.; Legendre, C. Dual Kidney Transplantation. Transplantation 2017, 101, 488–497. [Google Scholar] [CrossRef] [PubMed]
  22. Tanriover, B.; Mohan, S.; Cohen, D.J.; Radhakrishnan, J.; Nickolas, T.L.; Stone, P.W.; Tsapepas, D.S.; Crew, R.J.; Dube, G.K.; Sandoval, P.R.; et al. Kidneys at Higher Risk of Discard: Expanding the Role of Dual Kidney Transplantation. Am. J. Transplant. 2014, 14, 404–415. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  23. Bresnahan, B.A.; McBride, M.A.; Cherikh, W.S.; Hariharan, S. Risk factors for renal allograft survival from pediatric cadaver donors: An analysis of united network for organ sharing data1. Transplantation 2001, 72, 256–261. [Google Scholar] [CrossRef] [PubMed]
  24. Aawsaj, Y.; Dosani, T.; Talbot, D. Dual Kidney Transplantation: A Single-Center Experience. Transplant. Proc. 2015, 47, 1125–1127. [Google Scholar] [CrossRef] [PubMed]
  25. Boggi, U.; Barsotti, M.; Collini, A.; Bernini, M.; Vistoli, F.; Paleologo, G.; Bianchi, A.; Tregnaghi, C.; Nerucci, B.; Ruggieri, G.; et al. Kidney Transplantation from Donors Aged 65 Years or More as Single or Dual Grafts. Transplant. Proc. 2005, 37, 577–580. [Google Scholar] [CrossRef] [PubMed]
  26. Casati, C.; Colombo, V.G.; Perrino, M.; Rossetti, O.M.; Querques, M.; Giacomoni, A.; Binaggia, A.; Colussi, G. Renal Transplants from Older Deceased Donors: Use of Preimplantation Biopsy and Differential Allocation to Dual or Single Kidney Transplant according to Histological Score Has No Advantages over Allocation to Single Kidney Transplant by Simple Clinical Indication. J. Transplant. 2018, 2018, 1–12. [Google Scholar] [CrossRef] [Green Version]
  27. De Paolis, P.; Colonnelli, R.; Favarò, A.; Salem, F.; Vignally, P.; Carriero, C.; Iappelli, M.; Di Giulio, S. Expanded Criteria Donor Kidney Transplantation: Comparative Outcome Evaluation Between Single Versus Double Kidney Transplantation at 8 Years: A Single Center Experience. Transplant. Proc. 2016, 48, 329–332. [Google Scholar] [CrossRef]
  28. Dietl, K.-H.; Wolters, H.; Marschall, B.; Senninger, N.; Heidenreich, S. Cadaveric “two-in-one” kidney transplantation from marginal donors: Experience of 26 cases after 3 years. Transplantation 2000, 70, 790–794. [Google Scholar] [CrossRef]
  29. Furian, L.; Baldan, N.; Margani, G.; Ekser, B.; Silvestre, C.; Marchini, F.; Bonfante, L.; Rossi, B.; Valente, M.; Rigotti, P. Calcineurin inhibitor-free immunosuppression in dual kidney transplantation from elderly donors. Clin. Transplant. 2007, 21, 57–62. [Google Scholar] [CrossRef]
  30. Johnson, A.P.; Price, T.P.; Lieby, B.; Doria, C. Dual Kidney Allocation Score: A Novel Algorithm Utilizing Expanded Donor Criteria for the Allocation of Dual Kidneys in Adults. Ann. Transplant. 2016, 21, 565–576. [Google Scholar] [CrossRef]
  31. Klair, T.; Gregg, A.; Phair, J.; Kayler, L.K. Outcomes of Adult Dual Kidney Transplants by KDRI in the United States. Am. J. Transplant. 2013, 13, 2433–2440. [Google Scholar] [CrossRef]
  32. Lee, K.W.; Park, J.B.; Cha, S.R.; Lee, S.H.; Chung, Y.J.; Yoo, H.; Kim, K.; Kim, S.J. Dual kidney transplantation offers a safe and effective way to use kidneys from deceased donors older than 70 years. BMC Nephrol. 2020, 21, 3. [Google Scholar] [CrossRef] [Green Version]
  33. Mallon, D.H.; Riddiough, G.E.; Summers, D.M.; Butler, A.J.; Callaghan, C.J.; Bradbury, L.L.; Bardsley, V.; Broecker, V.; Saeb-Parsy, K.; Torpey, N.; et al. Successful Transplantation of Kidneys from Elderly Circulatory Death Donors by Using Microscopic and Macroscopic Characteristics to Guide Single or Dual Implantation. Am. J. Transplant. 2015, 15, 2931–2939. [Google Scholar] [CrossRef]
  34. Perico, N.; Ruggenenti, P.; Scalamogna, M.; Locatelli, G.; Remuzzi, G. One or two marginal organs for kidney transplantation? Transplant. Proc. 2002, 34, 3091–3096. [Google Scholar] [CrossRef]
  35. Remuzzi, G.; Grinyò, J.; Ruggenenti, P.; Beatini, M.; Cole, E.H.; Milford, E.L.; Brenner, B.M. Early Experience with Dual Kidney Transplantation in Adults using Expanded Donor Criteria. J. Am. Soc. Nephrol. 1999, 10, 2591–2598. [Google Scholar] [CrossRef]
  36. Remuzzi, G.; Ruggenenti, P.; Ruggenenti, P. Renal transplantation: Single or dual for donors aging ≥60 years? Transplantation 2000, 69, 2000–2001. [Google Scholar] [CrossRef]
  37. Rigotti, P.; Cadrobbi, R.; Furian, L.; Baldan, N.; Sarzo, G.; Liberati, L.; Valente, M.; Ancona, E. Short-term outcome of dual kidney transplantation at a single center. Transplant. Proc. 2001, 33, 3771–3773. [Google Scholar] [CrossRef]
  38. Ruggenenti, P.; Silvestre, C.; Boschiero, L.; Rota, G.; Furian, L.; Perna, A.; Rossini, G.; Remuzzi, G.; Rigotti, P. Long-term outcome of renal transplantation from octogenarian donors: A multicenter controlled study. Am. J. Transplant. 2017, 17, 3159–3171. [Google Scholar] [CrossRef] [Green Version]
  39. Snanoudj, R.; Rabant, M.; Timsit, M.O.; Karras, A.; Savoye, E.; Tricot, L.; Loupy, A.; Hiesse, C.; Zuber, J.; Kreis, H.; et al. Donor-Estimated GFR as an Appropriate Criterion for Allocation of ECD Kidneys into Single or Dual Kidney Transplantation. Am. J. Transplant. 2009, 9, 2542–2551. [Google Scholar] [CrossRef]
  40. Wolters, H.H.; Palmes, D.; Heidenreich, S.; August, C.; Brockmann, J.; Senninger, N.; Dietl, K.-H. Long-term follow-up of double kidney transplantation using a score for evaluation of marginal donors*. Transpl. Int. 2005, 18, 453–457. [Google Scholar] [CrossRef]
  41. Ershoff, B.D.; Lee, C.K.; Wray, C.L.; Agopian, V.G.; Urban, G.; Baldi, P.; Cannesson, M. Training and Validation of Deep Neural Networks for the Prediction of 90-Day Post-Liver Transplant Mortality Using UNOS Registry Data. Transplant. Proc. 2020, 52, 246–258. [Google Scholar] [CrossRef] [PubMed]
  42. Thongprayoon, C.; Mao, S.A.; Jadlowiec, C.C.; Mao, M.A.; Leeaphorn, N.; Kaewput, W.; Vaitla, P.; Pattharanitima, P.; Tangpanithandee, S.; Krisanapan, P.; et al. Machine Learning Consensus Clustering of Morbidly Obese Kidney Transplant Recipients in the United States. J. Clin. Med. 2022, 11, 3288. [Google Scholar] [CrossRef] [PubMed]
  43. Thongprayoon, C.; Vaitla, P.; Jadlowiec, C.C.; Leeaphorn, N.; Mao, S.A.; Mao, M.A.; Pattharanitima, P.; Bruminhent, J.; Khoury, N.J.; Garovic, V.D.; et al. Use of Machine Learning Consensus Clustering to Identify Distinct Subtypes of Black Kidney Transplant Recipients and Associated Outcomes. JAMA Surg. 2022, 157, e221286. [Google Scholar] [CrossRef] [PubMed]
  44. Monti, S.; Tamayo, P.; Mesirov, J.; Golub, T. Consensus Clustering: A Resampling-Based Method for Class Discovery and Visualization of Gene Expression Microarray Data. Mach. Learn. 2003, 52, 91–118. [Google Scholar] [CrossRef]
  45. MacEachern, S.J.; Forkert, N.D. Machine learning for precision medicine. Genome 2021, 64, 416–425. [Google Scholar] [CrossRef]
  46. Alyousef, A.A.; Nihtyanova, S.; Denton, C.; Bosoni, P.; Bellazzi, R.; Tucker, A. Nearest Consensus Clustering Classification to Identify Subclasses and Predict Disease. J. Health Inform. Res. 2018, 2, 402–422. [Google Scholar] [CrossRef] [Green Version]
  47. Thongprayoon, C.; Jadlowiec, C.C.; Kaewput, W.; Vaitla, P.; Mao, S.A.; Mao, M.A.; Leeaphorn, N.; Qureshi, F.; Pattharanitima, P.; Qureshi, F.; et al. Distinct Phenotypes of Kidney Transplant Recipients in the United States with Limited Functional Status as Identified through Machine Learning Consensus Clustering. J. Pers. Med. 2022, 12, 859. [Google Scholar] [CrossRef]
  48. Van Buuren, S.; Groothuis-Oudshoorn, K. mice: Multivariate imputation by chained equations in R. J. Stat. Softw. 2011, 45, 1–67. [Google Scholar] [CrossRef] [Green Version]
  49. Wilkerson, M.D.; Hayes, D.N. ConsensusClusterPlus: A class discovery tool with confidence assessments and item tracking. Bioinformatics 2010, 26, 1572–1573. [Google Scholar] [CrossRef] [Green Version]
  50. Robinson, A. Allocation of Dual and En Bloc Kidneys Two Year Post-Implementation Monitoring Report; OPTN Kidney Transplantation Committee: 21 March 2022. Available online: https://optn.transplant.hrsa.gov/media/33faxsvb/data_report_kidney_full_20220321_508_remediated.pdf (accessed on 5 October 2022).
  51. Sharma, A.; Fisher, R.A.; Cotterell, A.H.; King, A.L.; Maluf, D.G.; Posner, M.P. En Bloc Kidney Transplantation from Pediatric Donors: Comparable Outcomes with Living Donor Kidney Transplantation. Transplantation 2011, 92, 564–569. [Google Scholar] [CrossRef]
  52. Jannat-Khah, D.P.; Unterbrink, M.; McNairy, M.; Pierre, S.; Fitzgerald, D.W.; Pape, J.; Evans, A. Treating loss-tofollow-up as a missing data problem: A case study using a longitudinal cohort of HIV-infected patients in Haiti. BMC Public Health 2018, 18, 1269. [Google Scholar] [CrossRef] [Green Version]
  53. Knol, M.J.; Janssen, K.J.; Donders, A.R.; Egberts, A.C.; Heerdink, E.R.; Grobbee, D.E.; Moons, K.G.; Geerlings, M.I. Unpredictable bias when using the missing indicator method or complete case analysis for missing confounder values: An empirical example. J. Clin. Epidemiol. 2010, 63, 728–736. [Google Scholar] [CrossRef]
  54. White, I.R.; Carlin, J.B. Bias and efficiency of multiple imputation compared with complete-case analysis for missing covariate values. Stat. Med. 2010, 29, 2920–2931. [Google Scholar] [CrossRef]
  55. White, I.R.; Royston, P.; Wood, A.M. Multiple imputation using chained equations: Issues and guidance for practice. Stat. Med. 2011, 30, 377–399. [Google Scholar] [CrossRef]
  56. Hedden, S.L.; Woolson, R.F.; Carter, R.E.; Palesch, Y.; Upadhyaya, H.P.; Malcolm, R.J. The impact of loss to follow up on hypothesis tests of the treatment effect for several statistical methods in substance abuse clinical trials. J. Subst. Abuse Treat. 2009, 37, 54–63. [Google Scholar] [CrossRef] [Green Version]
  57. Donders, A.R.T.; Van Der Heijden, G.J.; Stijnen, T.; Moons, K.G. A gentle introduction to imputation of missing values. J. Clin. Epidemiol. 2006, 59, 1087–1091. [Google Scholar] [CrossRef]
  58. Șenbabaoğlu, Y.; Michailidis, G.; Li, J.Z. Critical limitations of consensus clustering in class discovery. Sci. Rep. 2014, 4, 6207. [Google Scholar] [CrossRef] [Green Version]
  59. Pattharanitima, P.; Thongprayoon, C.; Petnak, T.; Srivali, N.; Gembillo, G.; Kaewput, W.; Chesdachai, S.; Vallabhajosyula, S.; O’Corragain, O.A.; Mao, M.A.; et al. Machine Learning Consensus Clustering Approach for Patients with Lactic Acidosis in Intensive Care Units. J. Pers. Med. 2021, 11, 1132. [Google Scholar] [CrossRef]
  60. Thongprayoon, C.; Dumancas, C.Y.; Nissaisorakarn, V.; Keddis, M.T.; Kattah, A.G.; Pattharanitima, P.; Petnak, T.; Vallabhajosyula, S.; Garovic, V.D.; Mao, M.A.; et al. Machine Learning Consensus Clustering Approach for Hospitalized Patients with Phosphate Derangements. J. Clin. Med. 2021, 10, 4441. [Google Scholar] [CrossRef]
  61. Thongprayoon, C.; Hansrivijit, P.; Mao, M.A.; Vaitla, P.K.; Kattah, A.G.; Pattharanitima, P.; Vallabhajosyula, S.; Nissaisorakarn, V.; Petnak, T.; Keddis, M.T.; et al. Machine Learning Consensus Clustering of Hospitalized Patients with Admission Hyponatremia. Diseases 2021, 9, 54. [Google Scholar] [CrossRef]
  62. Thongprayoon, C.; Kattah, A.G.; Mao, M.A.; Keddis, M.T.; Pattharanitima, P.; Vallabhajosyula, S.; Nissaisorakarn, V.; Erickson, S.B.; Dillon, J.J.; Garovic, V.D.; et al. Distinct phenotypes of hospitalized patients with hyperkalemia by machine learning consensus clustering and associated mortality risks. QJM Int. J. Med. 2022, 115, 442–449. [Google Scholar] [CrossRef] [PubMed]
  63. Thongprayoon, C.; Mao, M.A.; Kattah, A.G.; Keddis, M.T.; Pattharanitima, P.; Erickson, S.B.; Dillon, J.J.; Garovic, V.D.; Cheungpasitporn, W. Subtyping hospitalized patients with hypokalemia by machine learning consensus clustering and associated mortality risks. Clin. Kidney J. 2022, 15, 253–261. [Google Scholar] [CrossRef] [PubMed]
  64. Thongprayoon, C.; Mao, M.A.; Keddis, M.T.; Kattah, A.G.; Chong, G.Y.; Pattharanitima, P.; Nissaisorakarn, V.; Garg, A.K.; Erickson, S.B.; Dillon, J.J.; et al. Hypernatremia subgroups among hospitalized patients by machine learning consensus clustering with different patient survival. J. Nephrol. 2022, 35, 921–929. [Google Scholar] [CrossRef] [PubMed]
  65. Thongprayoon, C.; Nissaisorakarn, V.; Pattharanitima, P.; Mao, M.A.; Kattah, A.G.; Keddis, M.T.; Dumancas, C.Y.; Vallabhajosyula, S.; Petnak, T.; Erickson, S.B.; et al. Subtyping Hyperchloremia among Hospitalized Patients by Machine Learning Consensus Clustering. Medicina 2021, 57, 903. [Google Scholar] [CrossRef]
  66. Thongprayoon, C.; Sy-Go, J.P.T.; Nissaisorakarn, V.; Dumancas, C.Y.; Keddis, M.T.; Kattah, A.G.; Pattharanitima, P.; Vallabhajosyula, S.; Mao, M.A.; Qureshi, F.; et al. Machine Learning Consensus Clustering Approach for Hospitalized Patients with Dysmagnesemia. Diagnostics 2021, 11, 2119. [Google Scholar] [CrossRef]
  67. Thongprayoon, C.; Vaitla, P.; Nissaisorakarn, V.; Mao, M.A.; Genovez, J.L.Z.; Kattah, A.G.; Pattharanitima, P.; Vallabhajosyula, S.; Keddis, M.T.; Qureshi, F.; et al. Clinically Distinct Subtypes of Acute Kidney Injury on Hospital Admission Identified by Machine Learning Consensus Clustering. Med. Sci. 2021, 9, 60. [Google Scholar] [CrossRef]
Medicina 58 01831 g001 550
Figure 1. (A) Consensus CDF plot; (B) Delta area plot; (C) Consensus matrix heat map.
Figure 1. (A) Consensus CDF plot; (B) Delta area plot; (C) Consensus matrix heat map.
Medicina 58 01831 g001
Medicina 58 01831 g002 550
Figure 2. Mean consensus score for different numbers of clusters.
Figure 2. Mean consensus score for different numbers of clusters.
Medicina 58 01831 g002
Medicina 58 01831 g003 550
Figure 3. The standardized differences across two DKT clusters for each of baseline parameters.
Figure 3. The standardized differences across two DKT clusters for each of baseline parameters.
Medicina 58 01831 g003
Medicina 58 01831 g004 550
Figure 4. (A) Patient survival; (B) Death-censored graft survival outcomes among two identified clusters of DKT patients.
Figure 4. (A) Patient survival; (B) Death-censored graft survival outcomes among two identified clusters of DKT patients.
Medicina 58 01831 g004
Table
Table 1. Clinical characteristics of DKT patients according to the assigned clusters.
Table 1. Clinical characteristics of DKT patients according to the assigned clusters.
All
(n = 2821)		Cluster 1
(n = 1875)		Cluster 2
(n = 946)		p-Value
Recipient Age (year)53.7 ± 13.848.9 ± 13.463.2 ± 8.8<0.001
Recipient male sex1511 (54)882 (47)629 (66)<0.001
Recipient race <0.001
 -
White
1038 (37)596 (32)442 (47)
 -
Black
815 (29)565 (30)250 (26)
 -
Hispanic
494 (18)346 (18)148 (16)
 -
Other
474 (17)368 (20)106 (11)
ABO blood group 0.239
 -
A
955 (34)621 (33)334 (35)
 -
B
431 (15)287 (15)144 (15)
 -
AB
144 (5)106 (6)38 (4)
 -
O
1291 (46)861 (46)430 (45)
Body mass index (kg/m2)26.2 ± 4.725.3 ± 4.428.2 ± 4.8<0.001
Kidney retransplant131 (4.6)120 (6)11 (1)<0.001
Dialysis duration <0.001
 -
Preemptive
297 (11)180 (10)117 (12)
 -
<1 year
308 (11)179 (10)129 (14)
 -
1–3 years
809 (29)489 (26)320 (34)
 -
>3 years
1407 (50)1027 (55)380 (40)
Cause of ESKD <0.001
 -
Diabetes mellitus
746 (26)362 (19)384 (41)
 -
Hypertension
738 (26)477 (25)261 (28)
 -
Glomerular disease
626 (22)499 (27)127 (13)
 -
Polycystic kidney disease
232 (8)159 (8)73 (8)
 -
Other
479 (17)378 (20)101 (11)
Comorbidity
 -
Diabetes mellitus
920 (33)455 (24)465 (49)<0.001
 -
Malignancy
233 (8)135 (7)98 (10)0.004
 -
Peripheral vascular disease
214 (8)113 (6)101 (11)<0.001
Panel reactive antibody, median (IQR)0 (0, 11)0 (0, 23)0 (0, 0)<0.001
Positive Hepatitis C virus serostatus97 (3)55 (3)42 (4)0.038
Positive Hepatitis B surface antigen64 (2)48 (3)16 (2)0.144
Positive Human immunodeficiency virus serostatus28 (1)22 (1)6 (1)0.173
Functional status 0.267
 -
10–30%
7 (0)5 (0)2 (0.21)
 -
40–70%
1116 (40)722 (39)394 (42)
 -
80–100%
1698 (60)1148 (61)550 (58)
Working income771 (27)571 (30)200 (21)<0.001
Public insurance2125 (75)1376 (73)749 (79)0.001
US resident2776 (98)1835 (97)941 (99)0.001
Undergraduate education or above1434 (51)946 (50)488 (52)0.570
Serum albumin (g/dL)4 ± 0.64.0 ± 0.63.9 ± 0.60.005
Kidney donor status <0.001
 -
Non-ECD deceased
2152 (76)1872 (100)280 (30)
 -
ECD deceased
669 (24)3 (0)666 (70)
Donor age21.9 ± 28.13.0 ± 8.059.3 ± 10.9<0.001
Donor male sex1482 (53)1079 (58)403 (43)<0.001
Donor race <0.001
 -
White
1724 (61)1063 (57)661 (70)
 -
Black
555 (20)410 (22)145 (15)
 -
Hispanic
386 (14)308 (16)78 (8)
 -
Other
156 (6)94 (5)62 (7)
History of hypertension in donor651 (23)27 (1)624 (66)<0.001
Kidney donor profile index (KDPI) <0.001
 -
KDPI < 85
1981 (70)1593 (85)388 (41)
 -
KDPI ≥ 85
840 (30)282 (15)558 (59)
HLA mismatch, median (IQR)5 (4, 5)5 (4, 5)5 (4, 5)0.06
Cold ischemia time (hours)19.6 ± 10.118.0 ± 9.322.9 ± 10.9<0.001
Kidney on pump1028 (36)385 (21)643 (68)<0.001
Delay graft function660 (23)324 (17)336 (36)<0.001
Allocation type 0.001
 -
Local
1509 (53)965 (51)544 (58)
 -
Regional
654 (23)476 (25)178 (19)
 -
National
658 (23)434 (23)224 (24)
Epstein–Barr virus status <0.001
 -
Low risk
64 (2)63 (3)1 (0)
 -
Moderate risk
2588 (92)1746 (93)842 (89)
 -
High risk
169 (6)66 (4)103 (11)
Cytomegalovirus status <0.001
 -
D−/R−
380 (13)280 (15)100 (11)
 -
D−/R+
954 (34)763 (41)191 (20)
 -
D+/R+
1084 (38)608 (32)476 (50)
 -
D+/R−
403 (14)224 (12)179 (19)
Induction immunosuppression
 -
Thymoglobulin
1732 (61)1236 (66)496 (52)<0.001
 -
Alemtuzumab
353 (13)213 (11)140 (15)0.009
 -
Basiliximab
582 (21)315 (17)267 (28)<0.001
 -
Other
87 (3)54 (3)33 (3)0.378
 -
No induction
173 (6)111 (6)62 (7)0.508
Maintenance Immunosuppression
 -
Tacrolimus
2557 (91)1713 (91)844 (89)0.065
 -
Cyclosporine
29 (1)17 (1)12 (1)0.368
 -
Mycophenolate
2604 (92)1739 (93)865 (91)0.218
 -
Azathioprine
7 (0)7 (0)0 (0)0.060
 -
mTOR inhibitors
9 (0)4 (0)5 (1)0.161
 -
Steroid
1954 (69)1270 (68)684 (72)0.013
Abbreviations: D: Donor, ECD: Extended criteria donor, ESKD: end stage kidney disease, mTOR: Mammalian target of rapamycin, R: Recipient.
Table
Table 2. Clinical outcomes.
Table 2. Clinical outcomes.
Cluster 1Cluster 2p-Value
1-year survival98.0%94.6%<0.001
HR for 1-year mortality1 (ref)2.62 (1.70–4.08)<0.001
5-year survival92.1%76.3%<0.001
HR for 5-year mortality1 (ref)3.12 (2.41–4.05)<0.001
1-year death-censored graft survival93.5%94.9%0.08
HR for 1-year death-censored graft loss1 (ref)0.73 (0.51–1.03)0.08
5-year death-censored graft survival89.2%84.8%0.28
HR for 5-year death-censored graft loss1 (ref)1.15 (0.89–1.48)0.28
1-year acute rejection4.2%6.1%0.03
OR for 1-year acute rejection1 (ref)1.48 (1.05–2.10)0.03
Table
Table 3. Subgroup analysis.
Table 3. Subgroup analysis.
Patient DeathDeath-Censored Graft Failure
HR (95% CI)p-ValueHR (95% CI)p-Value
Recipient age
 -
<60
1.94 (1.13–3.21)0.021.26 (0.85–1.83)0.25
 -
≥60
2.00 (1.42–2.87)<0.0011.41 (0.91–2.21)0.12
Recipient sex
 -
Male
2.92 (2.11–4.10)<0.0011.47 (1.03–2.10)0.03
 -
Female
3.03 (1.95–4.68)<0.0011.00 (0.66–1.46)0.99
Recipient race
 -
White
3.12 (2.11–4.69)<0.0011.03 (0.68–1.55)0.89
 -
Non-white
2.89 (2.04–4.12)<0.0011.25 (0.90–1.72)0.18
Recipient body mass index
 -
<30
3.20 (2.36–4.34)<0.0011.11 (0.81–1.50)0.52
 -
≥30
2.22 (1.34–3.82)0.0021.05 (0.64–1.74)0.84
Kidney retransplant
 -
No
3.25 (2.49–4.27)<0.0011.14 (0.88–1.48)0.33
 -
Yes
3.59 (0.81–11.55)0.092.95 (0.68–9.18)0.13
Preemptive transplant
 -
No
3.08 (2.35–4.03)<0.0011.21 (0.92–1.57)0.16
 -
Yes
4.43 (1.64–13.94)0.0030.71 (0.25–1.78)0.48
Recipient diabetes
 -
No
3.61 (2.50–5.22)<0.0011.15 (0.82–1.60)0.41
 -
Yes
1.84 (1.27–2.69)0.0011.11 (0.73–1.70)0.63
PRA
 -
0
3.15 (2.31–4.33)<0.0011.14 (0.84–1.54)0.39
 -
>0
3.13 (1.94–5.05)<0.0011.22 (0.74–1.94)0.42
Donor sex
 -
Male
3.46 (2.46–4.89)<0.0011.49 (1.05–2.08)0.02
 -
Female
2.99 (2.01–4.50)<0.0010.90 (0.61–1.33)0.60
Donor race
 -
White
3.12 (2.23–4.38)<0.0011.02 (0.74–1.40)0.91
 -
Non-White
3.23 (2.12–4.91)<0.0011.44 (0.95–2.19)0.10
Donor hypertension
 -
No
2.92 (2.03–4.13)<0.0011.11 (0.75–1.61)0.58
 -
Yes
2.52 (0.80–15.30)0.130.77 (0.32–2.52)0.61
KDPI
 -
<85
2.30 (1.56–3.33)<0.0011.21 (0.82–1.73)0.33
 -
≥85
3.12 (1.94–5.34)<0.0010.69 (0.46–1.03)0.07
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Share and Cite

MDPI and ACS Style

Tangpanithandee, S.; Thongprayoon, C.; Jadlowiec, C.C.; Mao, S.A.; Mao, M.A.; Vaitla, P.; Leeaphorn, N.; Kaewput, W.; Pattharanitima, P.; Krisanapan, P.; et al. Clinical Phenotypes of Dual Kidney Transplant Recipients in the United States as Identified through Machine Learning Consensus Clustering. Medicina 2022, 58, 1831. https://0-doi-org.brum.beds.ac.uk/10.3390/medicina58121831

AMA Style

Tangpanithandee S, Thongprayoon C, Jadlowiec CC, Mao SA, Mao MA, Vaitla P, Leeaphorn N, Kaewput W, Pattharanitima P, Krisanapan P, et al. Clinical Phenotypes of Dual Kidney Transplant Recipients in the United States as Identified through Machine Learning Consensus Clustering. Medicina. 2022; 58(12):1831. https://0-doi-org.brum.beds.ac.uk/10.3390/medicina58121831

Chicago/Turabian Style

Tangpanithandee, Supawit, Charat Thongprayoon, Caroline C. Jadlowiec, Shennen A. Mao, Michael A. Mao, Pradeep Vaitla, Napat Leeaphorn, Wisit Kaewput, Pattharawin Pattharanitima, Pajaree Krisanapan, and et al. 2022. "Clinical Phenotypes of Dual Kidney Transplant Recipients in the United States as Identified through Machine Learning Consensus Clustering" Medicina 58, no. 12: 1831. https://0-doi-org.brum.beds.ac.uk/10.3390/medicina58121831

Article Metrics

Back to TopTop